{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.926829268292683, "global_step": 840, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 0.0, "loss": 0.9326, "step": 1 }, { "epoch": 0.01, "learning_rate": 3.899180437875726e-06, "loss": 0.9014, "step": 2 }, { "epoch": 0.01, "learning_rate": 6.1800547775785244e-06, "loss": 0.8828, "step": 3 }, { "epoch": 0.01, "learning_rate": 7.798360875751452e-06, "loss": 0.8145, "step": 4 }, { "epoch": 0.02, "learning_rate": 9.053616605738856e-06, "loss": 0.7803, "step": 5 }, { "epoch": 0.02, "learning_rate": 1.007923521545425e-05, "loss": 0.7842, "step": 6 }, { "epoch": 0.02, "learning_rate": 1.0946383394261144e-05, "loss": 0.7754, "step": 7 }, { "epoch": 0.03, "learning_rate": 1.169754131362718e-05, "loss": 0.7061, "step": 8 }, { "epoch": 0.03, "learning_rate": 1.2360109555157049e-05, "loss": 0.7168, "step": 9 }, { "epoch": 0.03, "learning_rate": 1.2952797043614585e-05, "loss": 0.7148, "step": 10 }, { "epoch": 0.04, "learning_rate": 1.348894809355931e-05, "loss": 0.7031, "step": 11 }, { "epoch": 0.04, "learning_rate": 1.3978415653329978e-05, "loss": 0.7236, "step": 12 }, { "epoch": 0.05, "learning_rate": 1.4428682160514114e-05, "loss": 0.7021, "step": 13 }, { "epoch": 0.05, "learning_rate": 1.484556383213687e-05, "loss": 0.6875, "step": 14 }, { "epoch": 0.05, "learning_rate": 1.5233671383317381e-05, "loss": 0.7129, "step": 15 }, { "epoch": 0.06, "learning_rate": 1.5596721751502905e-05, "loss": 0.6943, "step": 16 }, { "epoch": 0.06, "learning_rate": 1.593775515114726e-05, "loss": 0.6836, "step": 17 }, { "epoch": 0.06, "learning_rate": 1.6259289993032772e-05, "loss": 0.668, "step": 18 }, { "epoch": 0.07, "learning_rate": 1.6563435861933304e-05, "loss": 0.6621, "step": 19 }, { "epoch": 0.07, "learning_rate": 1.685197748149031e-05, "loss": 0.6455, "step": 20 }, { "epoch": 0.07, "learning_rate": 1.7126438171839668e-05, "loss": 0.6631, "step": 21 }, { "epoch": 0.08, "learning_rate": 1.7388128531435038e-05, "loss": 0.6348, "step": 22 }, { "epoch": 0.08, "learning_rate": 1.7638184288576362e-05, "loss": 0.6602, "step": 23 }, { "epoch": 0.08, "learning_rate": 1.7877596091205705e-05, "loss": 0.6006, "step": 24 }, { "epoch": 0.09, "learning_rate": 1.810723321147771e-05, "loss": 0.6777, "step": 25 }, { "epoch": 0.09, "learning_rate": 1.832786259838984e-05, "loss": 0.6318, "step": 26 }, { "epoch": 0.09, "learning_rate": 1.8540164332735572e-05, "loss": 0.6406, "step": 27 }, { "epoch": 0.1, "learning_rate": 1.8744744270012596e-05, "loss": 0.6396, "step": 28 }, { "epoch": 0.1, "learning_rate": 1.8942144463773483e-05, "loss": 0.6348, "step": 29 }, { "epoch": 0.1, "learning_rate": 1.9132851821193106e-05, "loss": 0.6484, "step": 30 }, { "epoch": 0.11, "learning_rate": 1.9317305338856604e-05, "loss": 0.6133, "step": 31 }, { "epoch": 0.11, "learning_rate": 1.9495902189378633e-05, "loss": 0.6211, "step": 32 }, { "epoch": 0.11, "learning_rate": 1.9669002871137834e-05, "loss": 0.6299, "step": 33 }, { "epoch": 0.12, "learning_rate": 1.9836935589022987e-05, "loss": 0.6162, "step": 34 }, { "epoch": 0.12, "learning_rate": 1.9999999999999998e-05, "loss": 0.6201, "step": 35 }, { "epoch": 0.13, "learning_rate": 2e-05, "loss": 0.6279, "step": 36 }, { "epoch": 0.13, "learning_rate": 1.9975786924939468e-05, "loss": 0.6289, "step": 37 }, { "epoch": 0.13, "learning_rate": 1.9951573849878937e-05, "loss": 0.6152, "step": 38 }, { "epoch": 0.14, "learning_rate": 1.9927360774818403e-05, "loss": 0.6318, "step": 39 }, { "epoch": 0.14, "learning_rate": 1.990314769975787e-05, "loss": 0.6094, "step": 40 }, { "epoch": 0.14, "learning_rate": 1.987893462469734e-05, "loss": 0.6416, "step": 41 }, { "epoch": 0.15, "learning_rate": 1.9854721549636805e-05, "loss": 0.6279, "step": 42 }, { "epoch": 0.15, "learning_rate": 1.9830508474576275e-05, "loss": 0.6348, "step": 43 }, { "epoch": 0.15, "learning_rate": 1.980629539951574e-05, "loss": 0.6318, "step": 44 }, { "epoch": 0.16, "learning_rate": 1.9782082324455207e-05, "loss": 0.6348, "step": 45 }, { "epoch": 0.16, "learning_rate": 1.9757869249394673e-05, "loss": 0.6201, "step": 46 }, { "epoch": 0.16, "learning_rate": 1.9733656174334143e-05, "loss": 0.6318, "step": 47 }, { "epoch": 0.17, "learning_rate": 1.970944309927361e-05, "loss": 0.6367, "step": 48 }, { "epoch": 0.17, "learning_rate": 1.9685230024213075e-05, "loss": 0.6172, "step": 49 }, { "epoch": 0.17, "learning_rate": 1.9661016949152545e-05, "loss": 0.624, "step": 50 }, { "epoch": 0.18, "learning_rate": 1.963680387409201e-05, "loss": 0.6348, "step": 51 }, { "epoch": 0.18, "learning_rate": 1.961259079903148e-05, "loss": 0.6182, "step": 52 }, { "epoch": 0.18, "learning_rate": 1.9588377723970946e-05, "loss": 0.6494, "step": 53 }, { "epoch": 0.19, "learning_rate": 1.9564164648910413e-05, "loss": 0.6025, "step": 54 }, { "epoch": 0.19, "learning_rate": 1.953995157384988e-05, "loss": 0.6279, "step": 55 }, { "epoch": 0.2, "learning_rate": 1.9515738498789348e-05, "loss": 0.6387, "step": 56 }, { "epoch": 0.2, "learning_rate": 1.9491525423728814e-05, "loss": 0.6064, "step": 57 }, { "epoch": 0.2, "learning_rate": 1.9467312348668284e-05, "loss": 0.6094, "step": 58 }, { "epoch": 0.21, "learning_rate": 1.944309927360775e-05, "loss": 0.626, "step": 59 }, { "epoch": 0.21, "learning_rate": 1.9418886198547216e-05, "loss": 0.6094, "step": 60 }, { "epoch": 0.21, "learning_rate": 1.9394673123486686e-05, "loss": 0.6182, "step": 61 }, { "epoch": 0.22, "learning_rate": 1.9370460048426152e-05, "loss": 0.6016, "step": 62 }, { "epoch": 0.22, "learning_rate": 1.9346246973365618e-05, "loss": 0.6289, "step": 63 }, { "epoch": 0.22, "learning_rate": 1.9322033898305087e-05, "loss": 0.6289, "step": 64 }, { "epoch": 0.23, "learning_rate": 1.9297820823244554e-05, "loss": 0.5928, "step": 65 }, { "epoch": 0.23, "learning_rate": 1.927360774818402e-05, "loss": 0.6182, "step": 66 }, { "epoch": 0.23, "learning_rate": 1.924939467312349e-05, "loss": 0.5918, "step": 67 }, { "epoch": 0.24, "learning_rate": 1.9225181598062955e-05, "loss": 0.6221, "step": 68 }, { "epoch": 0.24, "learning_rate": 1.9200968523002425e-05, "loss": 0.6162, "step": 69 }, { "epoch": 0.24, "learning_rate": 1.917675544794189e-05, "loss": 0.6162, "step": 70 }, { "epoch": 0.25, "learning_rate": 1.9152542372881357e-05, "loss": 0.6445, "step": 71 }, { "epoch": 0.25, "learning_rate": 1.9128329297820823e-05, "loss": 0.6172, "step": 72 }, { "epoch": 0.25, "learning_rate": 1.9104116222760293e-05, "loss": 0.6152, "step": 73 }, { "epoch": 0.26, "learning_rate": 1.907990314769976e-05, "loss": 0.6084, "step": 74 }, { "epoch": 0.26, "learning_rate": 1.9055690072639225e-05, "loss": 0.6162, "step": 75 }, { "epoch": 0.26, "learning_rate": 1.9031476997578695e-05, "loss": 0.5996, "step": 76 }, { "epoch": 0.27, "learning_rate": 1.900726392251816e-05, "loss": 0.6064, "step": 77 }, { "epoch": 0.27, "learning_rate": 1.898305084745763e-05, "loss": 0.5996, "step": 78 }, { "epoch": 0.28, "learning_rate": 1.8958837772397097e-05, "loss": 0.6328, "step": 79 }, { "epoch": 0.28, "learning_rate": 1.8934624697336563e-05, "loss": 0.6133, "step": 80 }, { "epoch": 0.28, "learning_rate": 1.891041162227603e-05, "loss": 0.6143, "step": 81 }, { "epoch": 0.29, "learning_rate": 1.88861985472155e-05, "loss": 0.5996, "step": 82 }, { "epoch": 0.29, "learning_rate": 1.8861985472154964e-05, "loss": 0.6182, "step": 83 }, { "epoch": 0.29, "learning_rate": 1.883777239709443e-05, "loss": 0.623, "step": 84 }, { "epoch": 0.3, "learning_rate": 1.88135593220339e-05, "loss": 0.6055, "step": 85 }, { "epoch": 0.3, "learning_rate": 1.8789346246973366e-05, "loss": 0.5967, "step": 86 }, { "epoch": 0.3, "learning_rate": 1.8765133171912836e-05, "loss": 0.5947, "step": 87 }, { "epoch": 0.31, "learning_rate": 1.8740920096852302e-05, "loss": 0.6182, "step": 88 }, { "epoch": 0.31, "learning_rate": 1.8716707021791768e-05, "loss": 0.6152, "step": 89 }, { "epoch": 0.31, "learning_rate": 1.8692493946731238e-05, "loss": 0.5977, "step": 90 }, { "epoch": 0.32, "learning_rate": 1.8668280871670704e-05, "loss": 0.6348, "step": 91 }, { "epoch": 0.32, "learning_rate": 1.864406779661017e-05, "loss": 0.6074, "step": 92 }, { "epoch": 0.32, "learning_rate": 1.8619854721549636e-05, "loss": 0.5898, "step": 93 }, { "epoch": 0.33, "learning_rate": 1.8595641646489106e-05, "loss": 0.5967, "step": 94 }, { "epoch": 0.33, "learning_rate": 1.8571428571428575e-05, "loss": 0.6113, "step": 95 }, { "epoch": 0.33, "learning_rate": 1.854721549636804e-05, "loss": 0.6123, "step": 96 }, { "epoch": 0.34, "learning_rate": 1.8523002421307507e-05, "loss": 0.6211, "step": 97 }, { "epoch": 0.34, "learning_rate": 1.8498789346246974e-05, "loss": 0.6006, "step": 98 }, { "epoch": 0.34, "learning_rate": 1.8474576271186443e-05, "loss": 0.6113, "step": 99 }, { "epoch": 0.35, "learning_rate": 1.845036319612591e-05, "loss": 0.6006, "step": 100 }, { "epoch": 0.35, "learning_rate": 1.8426150121065375e-05, "loss": 0.6123, "step": 101 }, { "epoch": 0.36, "learning_rate": 1.8401937046004845e-05, "loss": 0.5938, "step": 102 }, { "epoch": 0.36, "learning_rate": 1.837772397094431e-05, "loss": 0.6045, "step": 103 }, { "epoch": 0.36, "learning_rate": 1.835351089588378e-05, "loss": 0.5928, "step": 104 }, { "epoch": 0.37, "learning_rate": 1.8329297820823247e-05, "loss": 0.5977, "step": 105 }, { "epoch": 0.37, "learning_rate": 1.8305084745762713e-05, "loss": 0.6299, "step": 106 }, { "epoch": 0.37, "learning_rate": 1.828087167070218e-05, "loss": 0.5801, "step": 107 }, { "epoch": 0.38, "learning_rate": 1.825665859564165e-05, "loss": 0.6035, "step": 108 }, { "epoch": 0.38, "learning_rate": 1.8232445520581115e-05, "loss": 0.5938, "step": 109 }, { "epoch": 0.38, "learning_rate": 1.820823244552058e-05, "loss": 0.5977, "step": 110 }, { "epoch": 0.39, "learning_rate": 1.818401937046005e-05, "loss": 0.6016, "step": 111 }, { "epoch": 0.39, "learning_rate": 1.8159806295399516e-05, "loss": 0.5957, "step": 112 }, { "epoch": 0.39, "learning_rate": 1.8135593220338986e-05, "loss": 0.6113, "step": 113 }, { "epoch": 0.4, "learning_rate": 1.8111380145278452e-05, "loss": 0.6094, "step": 114 }, { "epoch": 0.4, "learning_rate": 1.8087167070217918e-05, "loss": 0.6016, "step": 115 }, { "epoch": 0.4, "learning_rate": 1.8062953995157388e-05, "loss": 0.6006, "step": 116 }, { "epoch": 0.41, "learning_rate": 1.8038740920096854e-05, "loss": 0.6182, "step": 117 }, { "epoch": 0.41, "learning_rate": 1.801452784503632e-05, "loss": 0.6025, "step": 118 }, { "epoch": 0.41, "learning_rate": 1.7990314769975786e-05, "loss": 0.5938, "step": 119 }, { "epoch": 0.42, "learning_rate": 1.7966101694915256e-05, "loss": 0.6172, "step": 120 }, { "epoch": 0.42, "learning_rate": 1.7941888619854725e-05, "loss": 0.6074, "step": 121 }, { "epoch": 0.43, "learning_rate": 1.791767554479419e-05, "loss": 0.6055, "step": 122 }, { "epoch": 0.43, "learning_rate": 1.7893462469733658e-05, "loss": 0.583, "step": 123 }, { "epoch": 0.43, "learning_rate": 1.7869249394673124e-05, "loss": 0.5918, "step": 124 }, { "epoch": 0.44, "learning_rate": 1.7845036319612593e-05, "loss": 0.6016, "step": 125 }, { "epoch": 0.44, "learning_rate": 1.782082324455206e-05, "loss": 0.6123, "step": 126 }, { "epoch": 0.44, "learning_rate": 1.7796610169491526e-05, "loss": 0.6104, "step": 127 }, { "epoch": 0.45, "learning_rate": 1.777239709443099e-05, "loss": 0.5801, "step": 128 }, { "epoch": 0.45, "learning_rate": 1.774818401937046e-05, "loss": 0.6035, "step": 129 }, { "epoch": 0.45, "learning_rate": 1.772397094430993e-05, "loss": 0.5811, "step": 130 }, { "epoch": 0.46, "learning_rate": 1.7699757869249397e-05, "loss": 0.5908, "step": 131 }, { "epoch": 0.46, "learning_rate": 1.7675544794188863e-05, "loss": 0.6035, "step": 132 }, { "epoch": 0.46, "learning_rate": 1.765133171912833e-05, "loss": 0.6094, "step": 133 }, { "epoch": 0.47, "learning_rate": 1.76271186440678e-05, "loss": 0.5957, "step": 134 }, { "epoch": 0.47, "learning_rate": 1.7602905569007265e-05, "loss": 0.6152, "step": 135 }, { "epoch": 0.47, "learning_rate": 1.757869249394673e-05, "loss": 0.5908, "step": 136 }, { "epoch": 0.48, "learning_rate": 1.75544794188862e-05, "loss": 0.5908, "step": 137 }, { "epoch": 0.48, "learning_rate": 1.7530266343825667e-05, "loss": 0.5957, "step": 138 }, { "epoch": 0.48, "learning_rate": 1.7506053268765136e-05, "loss": 0.585, "step": 139 }, { "epoch": 0.49, "learning_rate": 1.7481840193704602e-05, "loss": 0.6143, "step": 140 }, { "epoch": 0.49, "learning_rate": 1.745762711864407e-05, "loss": 0.6064, "step": 141 }, { "epoch": 0.49, "learning_rate": 1.7433414043583538e-05, "loss": 0.6025, "step": 142 }, { "epoch": 0.5, "learning_rate": 1.7409200968523004e-05, "loss": 0.583, "step": 143 }, { "epoch": 0.5, "learning_rate": 1.738498789346247e-05, "loss": 0.5967, "step": 144 }, { "epoch": 0.51, "learning_rate": 1.7360774818401936e-05, "loss": 0.5947, "step": 145 }, { "epoch": 0.51, "learning_rate": 1.7336561743341406e-05, "loss": 0.6123, "step": 146 }, { "epoch": 0.51, "learning_rate": 1.7312348668280875e-05, "loss": 0.627, "step": 147 }, { "epoch": 0.52, "learning_rate": 1.728813559322034e-05, "loss": 0.5986, "step": 148 }, { "epoch": 0.52, "learning_rate": 1.7263922518159808e-05, "loss": 0.623, "step": 149 }, { "epoch": 0.52, "learning_rate": 1.7239709443099274e-05, "loss": 0.6016, "step": 150 }, { "epoch": 0.53, "learning_rate": 1.7215496368038743e-05, "loss": 0.6016, "step": 151 }, { "epoch": 0.53, "learning_rate": 1.719128329297821e-05, "loss": 0.5928, "step": 152 }, { "epoch": 0.53, "learning_rate": 1.7167070217917676e-05, "loss": 0.582, "step": 153 }, { "epoch": 0.54, "learning_rate": 1.7142857142857142e-05, "loss": 0.5938, "step": 154 }, { "epoch": 0.54, "learning_rate": 1.711864406779661e-05, "loss": 0.6016, "step": 155 }, { "epoch": 0.54, "learning_rate": 1.709443099273608e-05, "loss": 0.584, "step": 156 }, { "epoch": 0.55, "learning_rate": 1.7070217917675547e-05, "loss": 0.5674, "step": 157 }, { "epoch": 0.55, "learning_rate": 1.7046004842615013e-05, "loss": 0.5957, "step": 158 }, { "epoch": 0.55, "learning_rate": 1.702179176755448e-05, "loss": 0.6035, "step": 159 }, { "epoch": 0.56, "learning_rate": 1.699757869249395e-05, "loss": 0.5879, "step": 160 }, { "epoch": 0.56, "learning_rate": 1.6973365617433415e-05, "loss": 0.5898, "step": 161 }, { "epoch": 0.56, "learning_rate": 1.694915254237288e-05, "loss": 0.5732, "step": 162 }, { "epoch": 0.57, "learning_rate": 1.692493946731235e-05, "loss": 0.5859, "step": 163 }, { "epoch": 0.57, "learning_rate": 1.6900726392251817e-05, "loss": 0.5908, "step": 164 }, { "epoch": 0.57, "learning_rate": 1.6876513317191286e-05, "loss": 0.6133, "step": 165 }, { "epoch": 0.58, "learning_rate": 1.6852300242130752e-05, "loss": 0.5645, "step": 166 }, { "epoch": 0.58, "learning_rate": 1.682808716707022e-05, "loss": 0.584, "step": 167 }, { "epoch": 0.59, "learning_rate": 1.6803874092009688e-05, "loss": 0.6035, "step": 168 }, { "epoch": 0.59, "learning_rate": 1.6779661016949154e-05, "loss": 0.5938, "step": 169 }, { "epoch": 0.59, "learning_rate": 1.675544794188862e-05, "loss": 0.5664, "step": 170 }, { "epoch": 0.6, "learning_rate": 1.6731234866828087e-05, "loss": 0.6064, "step": 171 }, { "epoch": 0.6, "learning_rate": 1.6707021791767556e-05, "loss": 0.5977, "step": 172 }, { "epoch": 0.6, "learning_rate": 1.6682808716707026e-05, "loss": 0.5889, "step": 173 }, { "epoch": 0.61, "learning_rate": 1.6658595641646492e-05, "loss": 0.6016, "step": 174 }, { "epoch": 0.61, "learning_rate": 1.6634382566585958e-05, "loss": 0.5986, "step": 175 }, { "epoch": 0.61, "learning_rate": 1.6610169491525424e-05, "loss": 0.5908, "step": 176 }, { "epoch": 0.62, "learning_rate": 1.6585956416464894e-05, "loss": 0.5811, "step": 177 }, { "epoch": 0.62, "learning_rate": 1.656174334140436e-05, "loss": 0.5791, "step": 178 }, { "epoch": 0.62, "learning_rate": 1.6537530266343826e-05, "loss": 0.5967, "step": 179 }, { "epoch": 0.63, "learning_rate": 1.6513317191283292e-05, "loss": 0.6055, "step": 180 }, { "epoch": 0.63, "learning_rate": 1.648910411622276e-05, "loss": 0.5977, "step": 181 }, { "epoch": 0.63, "learning_rate": 1.646489104116223e-05, "loss": 0.583, "step": 182 }, { "epoch": 0.64, "learning_rate": 1.6440677966101697e-05, "loss": 0.6162, "step": 183 }, { "epoch": 0.64, "learning_rate": 1.6416464891041163e-05, "loss": 0.6016, "step": 184 }, { "epoch": 0.64, "learning_rate": 1.639225181598063e-05, "loss": 0.5869, "step": 185 }, { "epoch": 0.65, "learning_rate": 1.63680387409201e-05, "loss": 0.5576, "step": 186 }, { "epoch": 0.65, "learning_rate": 1.6343825665859565e-05, "loss": 0.5938, "step": 187 }, { "epoch": 0.66, "learning_rate": 1.631961259079903e-05, "loss": 0.5879, "step": 188 }, { "epoch": 0.66, "learning_rate": 1.62953995157385e-05, "loss": 0.583, "step": 189 }, { "epoch": 0.66, "learning_rate": 1.6271186440677967e-05, "loss": 0.583, "step": 190 }, { "epoch": 0.67, "learning_rate": 1.6246973365617437e-05, "loss": 0.5781, "step": 191 }, { "epoch": 0.67, "learning_rate": 1.6222760290556903e-05, "loss": 0.5918, "step": 192 }, { "epoch": 0.67, "learning_rate": 1.619854721549637e-05, "loss": 0.5859, "step": 193 }, { "epoch": 0.68, "learning_rate": 1.617433414043584e-05, "loss": 0.6152, "step": 194 }, { "epoch": 0.68, "learning_rate": 1.6150121065375304e-05, "loss": 0.582, "step": 195 }, { "epoch": 0.68, "learning_rate": 1.612590799031477e-05, "loss": 0.5986, "step": 196 }, { "epoch": 0.69, "learning_rate": 1.6101694915254237e-05, "loss": 0.5752, "step": 197 }, { "epoch": 0.69, "learning_rate": 1.6077481840193706e-05, "loss": 0.5791, "step": 198 }, { "epoch": 0.69, "learning_rate": 1.6053268765133176e-05, "loss": 0.5732, "step": 199 }, { "epoch": 0.7, "learning_rate": 1.6029055690072642e-05, "loss": 0.6094, "step": 200 }, { "epoch": 0.7, "learning_rate": 1.6004842615012108e-05, "loss": 0.5996, "step": 201 }, { "epoch": 0.7, "learning_rate": 1.5980629539951574e-05, "loss": 0.6006, "step": 202 }, { "epoch": 0.71, "learning_rate": 1.5956416464891044e-05, "loss": 0.6113, "step": 203 }, { "epoch": 0.71, "learning_rate": 1.593220338983051e-05, "loss": 0.5889, "step": 204 }, { "epoch": 0.71, "learning_rate": 1.5907990314769976e-05, "loss": 0.5781, "step": 205 }, { "epoch": 0.72, "learning_rate": 1.5883777239709442e-05, "loss": 0.6113, "step": 206 }, { "epoch": 0.72, "learning_rate": 1.5859564164648912e-05, "loss": 0.5918, "step": 207 }, { "epoch": 0.72, "learning_rate": 1.583535108958838e-05, "loss": 0.5693, "step": 208 }, { "epoch": 0.73, "learning_rate": 1.5811138014527847e-05, "loss": 0.5986, "step": 209 }, { "epoch": 0.73, "learning_rate": 1.5786924939467314e-05, "loss": 0.5625, "step": 210 }, { "epoch": 0.74, "learning_rate": 1.576271186440678e-05, "loss": 0.5908, "step": 211 }, { "epoch": 0.74, "learning_rate": 1.573849878934625e-05, "loss": 0.5938, "step": 212 }, { "epoch": 0.74, "learning_rate": 1.5714285714285715e-05, "loss": 0.6123, "step": 213 }, { "epoch": 0.75, "learning_rate": 1.569007263922518e-05, "loss": 0.5879, "step": 214 }, { "epoch": 0.75, "learning_rate": 1.566585956416465e-05, "loss": 0.583, "step": 215 }, { "epoch": 0.75, "learning_rate": 1.5641646489104117e-05, "loss": 0.6094, "step": 216 }, { "epoch": 0.76, "learning_rate": 1.5617433414043587e-05, "loss": 0.624, "step": 217 }, { "epoch": 0.76, "learning_rate": 1.5593220338983053e-05, "loss": 0.5947, "step": 218 }, { "epoch": 0.76, "learning_rate": 1.556900726392252e-05, "loss": 0.6084, "step": 219 }, { "epoch": 0.77, "learning_rate": 1.554479418886199e-05, "loss": 0.5908, "step": 220 }, { "epoch": 0.77, "learning_rate": 1.5520581113801455e-05, "loss": 0.5938, "step": 221 }, { "epoch": 0.77, "learning_rate": 1.549636803874092e-05, "loss": 0.5625, "step": 222 }, { "epoch": 0.78, "learning_rate": 1.5472154963680387e-05, "loss": 0.583, "step": 223 }, { "epoch": 0.78, "learning_rate": 1.5447941888619856e-05, "loss": 0.5938, "step": 224 }, { "epoch": 0.78, "learning_rate": 1.5423728813559326e-05, "loss": 0.583, "step": 225 }, { "epoch": 0.79, "learning_rate": 1.5399515738498792e-05, "loss": 0.5918, "step": 226 }, { "epoch": 0.79, "learning_rate": 1.5375302663438258e-05, "loss": 0.582, "step": 227 }, { "epoch": 0.79, "learning_rate": 1.5351089588377724e-05, "loss": 0.5996, "step": 228 }, { "epoch": 0.8, "learning_rate": 1.5326876513317194e-05, "loss": 0.5684, "step": 229 }, { "epoch": 0.8, "learning_rate": 1.530266343825666e-05, "loss": 0.5996, "step": 230 }, { "epoch": 0.8, "learning_rate": 1.5278450363196126e-05, "loss": 0.5791, "step": 231 }, { "epoch": 0.81, "learning_rate": 1.5254237288135594e-05, "loss": 0.5869, "step": 232 }, { "epoch": 0.81, "learning_rate": 1.523002421307506e-05, "loss": 0.5625, "step": 233 }, { "epoch": 0.82, "learning_rate": 1.520581113801453e-05, "loss": 0.5771, "step": 234 }, { "epoch": 0.82, "learning_rate": 1.5181598062953998e-05, "loss": 0.5869, "step": 235 }, { "epoch": 0.82, "learning_rate": 1.5157384987893464e-05, "loss": 0.5654, "step": 236 }, { "epoch": 0.83, "learning_rate": 1.5133171912832932e-05, "loss": 0.5605, "step": 237 }, { "epoch": 0.83, "learning_rate": 1.5108958837772398e-05, "loss": 0.5967, "step": 238 }, { "epoch": 0.83, "learning_rate": 1.5084745762711865e-05, "loss": 0.5674, "step": 239 }, { "epoch": 0.84, "learning_rate": 1.5060532687651332e-05, "loss": 0.5889, "step": 240 }, { "epoch": 0.84, "learning_rate": 1.50363196125908e-05, "loss": 0.5947, "step": 241 }, { "epoch": 0.84, "learning_rate": 1.5012106537530267e-05, "loss": 0.5801, "step": 242 }, { "epoch": 0.85, "learning_rate": 1.4987893462469735e-05, "loss": 0.5771, "step": 243 }, { "epoch": 0.85, "learning_rate": 1.4963680387409203e-05, "loss": 0.6006, "step": 244 }, { "epoch": 0.85, "learning_rate": 1.493946731234867e-05, "loss": 0.5693, "step": 245 }, { "epoch": 0.86, "learning_rate": 1.4915254237288137e-05, "loss": 0.5898, "step": 246 }, { "epoch": 0.86, "learning_rate": 1.4891041162227605e-05, "loss": 0.5918, "step": 247 }, { "epoch": 0.86, "learning_rate": 1.4866828087167071e-05, "loss": 0.583, "step": 248 }, { "epoch": 0.87, "learning_rate": 1.4842615012106539e-05, "loss": 0.585, "step": 249 }, { "epoch": 0.87, "learning_rate": 1.4818401937046005e-05, "loss": 0.5664, "step": 250 }, { "epoch": 0.87, "learning_rate": 1.4794188861985473e-05, "loss": 0.5771, "step": 251 }, { "epoch": 0.88, "learning_rate": 1.4769975786924942e-05, "loss": 0.5771, "step": 252 }, { "epoch": 0.88, "learning_rate": 1.4745762711864408e-05, "loss": 0.6104, "step": 253 }, { "epoch": 0.89, "learning_rate": 1.4721549636803876e-05, "loss": 0.5732, "step": 254 }, { "epoch": 0.89, "learning_rate": 1.4697336561743342e-05, "loss": 0.5859, "step": 255 }, { "epoch": 0.89, "learning_rate": 1.467312348668281e-05, "loss": 0.6025, "step": 256 }, { "epoch": 0.9, "learning_rate": 1.4648910411622276e-05, "loss": 0.5869, "step": 257 }, { "epoch": 0.9, "learning_rate": 1.4624697336561744e-05, "loss": 0.6006, "step": 258 }, { "epoch": 0.9, "learning_rate": 1.460048426150121e-05, "loss": 0.585, "step": 259 }, { "epoch": 0.91, "learning_rate": 1.4576271186440678e-05, "loss": 0.5859, "step": 260 }, { "epoch": 0.91, "learning_rate": 1.4552058111380148e-05, "loss": 0.5654, "step": 261 }, { "epoch": 0.91, "learning_rate": 1.4527845036319614e-05, "loss": 0.5811, "step": 262 }, { "epoch": 0.92, "learning_rate": 1.4503631961259082e-05, "loss": 0.6006, "step": 263 }, { "epoch": 0.92, "learning_rate": 1.4479418886198548e-05, "loss": 0.5674, "step": 264 }, { "epoch": 0.92, "learning_rate": 1.4455205811138016e-05, "loss": 0.5996, "step": 265 }, { "epoch": 0.93, "learning_rate": 1.4430992736077482e-05, "loss": 0.5889, "step": 266 }, { "epoch": 0.93, "learning_rate": 1.440677966101695e-05, "loss": 0.585, "step": 267 }, { "epoch": 0.93, "learning_rate": 1.4382566585956417e-05, "loss": 0.5625, "step": 268 }, { "epoch": 0.94, "learning_rate": 1.4358353510895885e-05, "loss": 0.5791, "step": 269 }, { "epoch": 0.94, "learning_rate": 1.4334140435835353e-05, "loss": 0.5869, "step": 270 }, { "epoch": 0.94, "learning_rate": 1.4309927360774821e-05, "loss": 0.5918, "step": 271 }, { "epoch": 0.95, "learning_rate": 1.4285714285714287e-05, "loss": 0.5791, "step": 272 }, { "epoch": 0.95, "learning_rate": 1.4261501210653755e-05, "loss": 0.5674, "step": 273 }, { "epoch": 0.95, "learning_rate": 1.4237288135593221e-05, "loss": 0.5947, "step": 274 }, { "epoch": 0.96, "learning_rate": 1.4213075060532689e-05, "loss": 0.6133, "step": 275 }, { "epoch": 0.96, "learning_rate": 1.4188861985472155e-05, "loss": 0.5986, "step": 276 }, { "epoch": 0.97, "learning_rate": 1.4164648910411623e-05, "loss": 0.5996, "step": 277 }, { "epoch": 0.97, "learning_rate": 1.4140435835351092e-05, "loss": 0.5713, "step": 278 }, { "epoch": 0.97, "learning_rate": 1.4116222760290559e-05, "loss": 0.5762, "step": 279 }, { "epoch": 0.98, "learning_rate": 1.4092009685230026e-05, "loss": 0.5908, "step": 280 }, { "epoch": 0.98, "learning_rate": 1.4067796610169493e-05, "loss": 0.5703, "step": 281 }, { "epoch": 0.98, "learning_rate": 1.404358353510896e-05, "loss": 0.5596, "step": 282 }, { "epoch": 0.99, "learning_rate": 1.4019370460048427e-05, "loss": 0.5908, "step": 283 }, { "epoch": 0.99, "learning_rate": 1.3995157384987894e-05, "loss": 0.5674, "step": 284 }, { "epoch": 0.99, "learning_rate": 1.397094430992736e-05, "loss": 0.5781, "step": 285 }, { "epoch": 1.0, "learning_rate": 1.3946731234866828e-05, "loss": 0.5762, "step": 286 }, { "epoch": 1.0, "learning_rate": 1.3922518159806298e-05, "loss": 0.7271, "step": 287 }, { "epoch": 1.0, "learning_rate": 1.3898305084745764e-05, "loss": 0.3965, "step": 288 }, { "epoch": 1.01, "learning_rate": 1.3874092009685232e-05, "loss": 0.3896, "step": 289 }, { "epoch": 1.01, "learning_rate": 1.3849878934624698e-05, "loss": 0.4058, "step": 290 }, { "epoch": 1.01, "learning_rate": 1.3825665859564166e-05, "loss": 0.3989, "step": 291 }, { "epoch": 1.02, "learning_rate": 1.3801452784503632e-05, "loss": 0.4155, "step": 292 }, { "epoch": 1.02, "learning_rate": 1.37772397094431e-05, "loss": 0.4067, "step": 293 }, { "epoch": 1.02, "learning_rate": 1.3753026634382568e-05, "loss": 0.4009, "step": 294 }, { "epoch": 1.03, "learning_rate": 1.3728813559322034e-05, "loss": 0.416, "step": 295 }, { "epoch": 1.03, "learning_rate": 1.3704600484261503e-05, "loss": 0.4058, "step": 296 }, { "epoch": 1.03, "learning_rate": 1.368038740920097e-05, "loss": 0.3701, "step": 297 }, { "epoch": 1.04, "learning_rate": 1.3656174334140437e-05, "loss": 0.3926, "step": 298 }, { "epoch": 1.04, "learning_rate": 1.3631961259079905e-05, "loss": 0.3955, "step": 299 }, { "epoch": 1.05, "learning_rate": 1.3607748184019371e-05, "loss": 0.3755, "step": 300 }, { "epoch": 1.05, "learning_rate": 1.3583535108958839e-05, "loss": 0.3726, "step": 301 }, { "epoch": 1.05, "learning_rate": 1.3559322033898305e-05, "loss": 0.3911, "step": 302 }, { "epoch": 1.06, "learning_rate": 1.3535108958837773e-05, "loss": 0.3706, "step": 303 }, { "epoch": 1.06, "learning_rate": 1.351089588377724e-05, "loss": 0.3696, "step": 304 }, { "epoch": 1.06, "learning_rate": 1.3486682808716709e-05, "loss": 0.3804, "step": 305 }, { "epoch": 1.07, "learning_rate": 1.3462469733656177e-05, "loss": 0.373, "step": 306 }, { "epoch": 1.07, "learning_rate": 1.3438256658595643e-05, "loss": 0.3667, "step": 307 }, { "epoch": 1.07, "learning_rate": 1.341404358353511e-05, "loss": 0.3643, "step": 308 }, { "epoch": 1.08, "learning_rate": 1.3389830508474577e-05, "loss": 0.3457, "step": 309 }, { "epoch": 1.08, "learning_rate": 1.3365617433414045e-05, "loss": 0.3525, "step": 310 }, { "epoch": 1.08, "learning_rate": 1.334140435835351e-05, "loss": 0.356, "step": 311 }, { "epoch": 1.09, "learning_rate": 1.3317191283292979e-05, "loss": 0.3545, "step": 312 }, { "epoch": 1.09, "learning_rate": 1.3292978208232448e-05, "loss": 0.353, "step": 313 }, { "epoch": 1.09, "learning_rate": 1.3268765133171914e-05, "loss": 0.3447, "step": 314 }, { "epoch": 1.1, "learning_rate": 1.3244552058111382e-05, "loss": 0.3569, "step": 315 }, { "epoch": 1.1, "learning_rate": 1.3220338983050848e-05, "loss": 0.3545, "step": 316 }, { "epoch": 1.1, "learning_rate": 1.3196125907990316e-05, "loss": 0.3438, "step": 317 }, { "epoch": 1.11, "learning_rate": 1.3171912832929782e-05, "loss": 0.3423, "step": 318 }, { "epoch": 1.11, "learning_rate": 1.314769975786925e-05, "loss": 0.3594, "step": 319 }, { "epoch": 1.11, "learning_rate": 1.3123486682808718e-05, "loss": 0.3442, "step": 320 }, { "epoch": 1.12, "learning_rate": 1.3099273607748184e-05, "loss": 0.3662, "step": 321 }, { "epoch": 1.12, "learning_rate": 1.3075060532687653e-05, "loss": 0.3584, "step": 322 }, { "epoch": 1.13, "learning_rate": 1.305084745762712e-05, "loss": 0.3511, "step": 323 }, { "epoch": 1.13, "learning_rate": 1.3026634382566587e-05, "loss": 0.3711, "step": 324 }, { "epoch": 1.13, "learning_rate": 1.3002421307506055e-05, "loss": 0.3486, "step": 325 }, { "epoch": 1.14, "learning_rate": 1.2978208232445521e-05, "loss": 0.355, "step": 326 }, { "epoch": 1.14, "learning_rate": 1.295399515738499e-05, "loss": 0.3589, "step": 327 }, { "epoch": 1.14, "learning_rate": 1.2929782082324455e-05, "loss": 0.3447, "step": 328 }, { "epoch": 1.15, "learning_rate": 1.2905569007263923e-05, "loss": 0.3442, "step": 329 }, { "epoch": 1.15, "learning_rate": 1.288135593220339e-05, "loss": 0.335, "step": 330 }, { "epoch": 1.15, "learning_rate": 1.2857142857142859e-05, "loss": 0.3369, "step": 331 }, { "epoch": 1.16, "learning_rate": 1.2832929782082327e-05, "loss": 0.3467, "step": 332 }, { "epoch": 1.16, "learning_rate": 1.2808716707021793e-05, "loss": 0.3428, "step": 333 }, { "epoch": 1.16, "learning_rate": 1.278450363196126e-05, "loss": 0.3452, "step": 334 }, { "epoch": 1.17, "learning_rate": 1.2760290556900727e-05, "loss": 0.3428, "step": 335 }, { "epoch": 1.17, "learning_rate": 1.2736077481840195e-05, "loss": 0.3525, "step": 336 }, { "epoch": 1.17, "learning_rate": 1.2711864406779661e-05, "loss": 0.3398, "step": 337 }, { "epoch": 1.18, "learning_rate": 1.2687651331719129e-05, "loss": 0.3477, "step": 338 }, { "epoch": 1.18, "learning_rate": 1.2663438256658595e-05, "loss": 0.3433, "step": 339 }, { "epoch": 1.18, "learning_rate": 1.2639225181598064e-05, "loss": 0.3438, "step": 340 }, { "epoch": 1.19, "learning_rate": 1.2615012106537532e-05, "loss": 0.3442, "step": 341 }, { "epoch": 1.19, "learning_rate": 1.2590799031476998e-05, "loss": 0.3457, "step": 342 }, { "epoch": 1.2, "learning_rate": 1.2566585956416466e-05, "loss": 0.3374, "step": 343 }, { "epoch": 1.2, "learning_rate": 1.2542372881355932e-05, "loss": 0.333, "step": 344 }, { "epoch": 1.2, "learning_rate": 1.25181598062954e-05, "loss": 0.3486, "step": 345 }, { "epoch": 1.21, "learning_rate": 1.2493946731234868e-05, "loss": 0.3462, "step": 346 }, { "epoch": 1.21, "learning_rate": 1.2469733656174334e-05, "loss": 0.3335, "step": 347 }, { "epoch": 1.21, "learning_rate": 1.2445520581113804e-05, "loss": 0.3379, "step": 348 }, { "epoch": 1.22, "learning_rate": 1.242130750605327e-05, "loss": 0.3467, "step": 349 }, { "epoch": 1.22, "learning_rate": 1.2397094430992738e-05, "loss": 0.3481, "step": 350 }, { "epoch": 1.22, "learning_rate": 1.2372881355932205e-05, "loss": 0.354, "step": 351 }, { "epoch": 1.23, "learning_rate": 1.2348668280871672e-05, "loss": 0.3433, "step": 352 }, { "epoch": 1.23, "learning_rate": 1.232445520581114e-05, "loss": 0.3501, "step": 353 }, { "epoch": 1.23, "learning_rate": 1.2300242130750606e-05, "loss": 0.3369, "step": 354 }, { "epoch": 1.24, "learning_rate": 1.2276029055690073e-05, "loss": 0.3403, "step": 355 }, { "epoch": 1.24, "learning_rate": 1.225181598062954e-05, "loss": 0.3535, "step": 356 }, { "epoch": 1.24, "learning_rate": 1.2227602905569009e-05, "loss": 0.353, "step": 357 }, { "epoch": 1.25, "learning_rate": 1.2203389830508477e-05, "loss": 0.3555, "step": 358 }, { "epoch": 1.25, "learning_rate": 1.2179176755447943e-05, "loss": 0.3389, "step": 359 }, { "epoch": 1.25, "learning_rate": 1.2154963680387411e-05, "loss": 0.3657, "step": 360 }, { "epoch": 1.26, "learning_rate": 1.2130750605326877e-05, "loss": 0.3398, "step": 361 }, { "epoch": 1.26, "learning_rate": 1.2106537530266345e-05, "loss": 0.3374, "step": 362 }, { "epoch": 1.26, "learning_rate": 1.2082324455205811e-05, "loss": 0.3325, "step": 363 }, { "epoch": 1.27, "learning_rate": 1.2058111380145279e-05, "loss": 0.3452, "step": 364 }, { "epoch": 1.27, "learning_rate": 1.2033898305084745e-05, "loss": 0.3281, "step": 365 }, { "epoch": 1.28, "learning_rate": 1.2009685230024215e-05, "loss": 0.3228, "step": 366 }, { "epoch": 1.28, "learning_rate": 1.1985472154963682e-05, "loss": 0.353, "step": 367 }, { "epoch": 1.28, "learning_rate": 1.1961259079903149e-05, "loss": 0.3457, "step": 368 }, { "epoch": 1.29, "learning_rate": 1.1937046004842616e-05, "loss": 0.3506, "step": 369 }, { "epoch": 1.29, "learning_rate": 1.1912832929782082e-05, "loss": 0.3457, "step": 370 }, { "epoch": 1.29, "learning_rate": 1.188861985472155e-05, "loss": 0.3413, "step": 371 }, { "epoch": 1.3, "learning_rate": 1.1864406779661018e-05, "loss": 0.3462, "step": 372 }, { "epoch": 1.3, "learning_rate": 1.1840193704600484e-05, "loss": 0.3354, "step": 373 }, { "epoch": 1.3, "learning_rate": 1.1815980629539952e-05, "loss": 0.3452, "step": 374 }, { "epoch": 1.31, "learning_rate": 1.179176755447942e-05, "loss": 0.3594, "step": 375 }, { "epoch": 1.31, "learning_rate": 1.1767554479418888e-05, "loss": 0.3511, "step": 376 }, { "epoch": 1.31, "learning_rate": 1.1743341404358356e-05, "loss": 0.3521, "step": 377 }, { "epoch": 1.32, "learning_rate": 1.1719128329297822e-05, "loss": 0.3311, "step": 378 }, { "epoch": 1.32, "learning_rate": 1.169491525423729e-05, "loss": 0.3301, "step": 379 }, { "epoch": 1.32, "learning_rate": 1.1670702179176756e-05, "loss": 0.3564, "step": 380 }, { "epoch": 1.33, "learning_rate": 1.1646489104116224e-05, "loss": 0.3345, "step": 381 }, { "epoch": 1.33, "learning_rate": 1.162227602905569e-05, "loss": 0.355, "step": 382 }, { "epoch": 1.33, "learning_rate": 1.1598062953995158e-05, "loss": 0.3364, "step": 383 }, { "epoch": 1.34, "learning_rate": 1.1573849878934627e-05, "loss": 0.3335, "step": 384 }, { "epoch": 1.34, "learning_rate": 1.1549636803874093e-05, "loss": 0.3477, "step": 385 }, { "epoch": 1.34, "learning_rate": 1.1525423728813561e-05, "loss": 0.3433, "step": 386 }, { "epoch": 1.35, "learning_rate": 1.1501210653753027e-05, "loss": 0.3467, "step": 387 }, { "epoch": 1.35, "learning_rate": 1.1476997578692495e-05, "loss": 0.3462, "step": 388 }, { "epoch": 1.36, "learning_rate": 1.1452784503631961e-05, "loss": 0.3354, "step": 389 }, { "epoch": 1.36, "learning_rate": 1.1428571428571429e-05, "loss": 0.334, "step": 390 }, { "epoch": 1.36, "learning_rate": 1.1404358353510895e-05, "loss": 0.3354, "step": 391 }, { "epoch": 1.37, "learning_rate": 1.1380145278450365e-05, "loss": 0.3501, "step": 392 }, { "epoch": 1.37, "learning_rate": 1.1355932203389833e-05, "loss": 0.3564, "step": 393 }, { "epoch": 1.37, "learning_rate": 1.1331719128329299e-05, "loss": 0.3442, "step": 394 }, { "epoch": 1.38, "learning_rate": 1.1307506053268767e-05, "loss": 0.333, "step": 395 }, { "epoch": 1.38, "learning_rate": 1.1283292978208233e-05, "loss": 0.3428, "step": 396 }, { "epoch": 1.38, "learning_rate": 1.12590799031477e-05, "loss": 0.3564, "step": 397 }, { "epoch": 1.39, "learning_rate": 1.1234866828087168e-05, "loss": 0.3359, "step": 398 }, { "epoch": 1.39, "learning_rate": 1.1210653753026634e-05, "loss": 0.3335, "step": 399 }, { "epoch": 1.39, "learning_rate": 1.1186440677966102e-05, "loss": 0.3462, "step": 400 }, { "epoch": 1.4, "learning_rate": 1.116222760290557e-05, "loss": 0.3408, "step": 401 }, { "epoch": 1.4, "learning_rate": 1.1138014527845038e-05, "loss": 0.3335, "step": 402 }, { "epoch": 1.4, "learning_rate": 1.1113801452784506e-05, "loss": 0.3457, "step": 403 }, { "epoch": 1.41, "learning_rate": 1.1089588377723972e-05, "loss": 0.3457, "step": 404 }, { "epoch": 1.41, "learning_rate": 1.106537530266344e-05, "loss": 0.3477, "step": 405 }, { "epoch": 1.41, "learning_rate": 1.1041162227602906e-05, "loss": 0.3564, "step": 406 }, { "epoch": 1.42, "learning_rate": 1.1016949152542374e-05, "loss": 0.3135, "step": 407 }, { "epoch": 1.42, "learning_rate": 1.099273607748184e-05, "loss": 0.3438, "step": 408 }, { "epoch": 1.43, "learning_rate": 1.0968523002421308e-05, "loss": 0.3389, "step": 409 }, { "epoch": 1.43, "learning_rate": 1.0944309927360777e-05, "loss": 0.3447, "step": 410 }, { "epoch": 1.43, "learning_rate": 1.0920096852300243e-05, "loss": 0.3428, "step": 411 }, { "epoch": 1.44, "learning_rate": 1.0895883777239711e-05, "loss": 0.3545, "step": 412 }, { "epoch": 1.44, "learning_rate": 1.0871670702179177e-05, "loss": 0.3394, "step": 413 }, { "epoch": 1.44, "learning_rate": 1.0847457627118645e-05, "loss": 0.3442, "step": 414 }, { "epoch": 1.45, "learning_rate": 1.0823244552058111e-05, "loss": 0.3237, "step": 415 }, { "epoch": 1.45, "learning_rate": 1.079903147699758e-05, "loss": 0.3286, "step": 416 }, { "epoch": 1.45, "learning_rate": 1.0774818401937045e-05, "loss": 0.3296, "step": 417 }, { "epoch": 1.46, "learning_rate": 1.0750605326876513e-05, "loss": 0.3447, "step": 418 }, { "epoch": 1.46, "learning_rate": 1.0726392251815983e-05, "loss": 0.3301, "step": 419 }, { "epoch": 1.46, "learning_rate": 1.0702179176755449e-05, "loss": 0.3398, "step": 420 }, { "epoch": 1.47, "learning_rate": 1.0677966101694917e-05, "loss": 0.3452, "step": 421 }, { "epoch": 1.47, "learning_rate": 1.0653753026634383e-05, "loss": 0.3608, "step": 422 }, { "epoch": 1.47, "learning_rate": 1.062953995157385e-05, "loss": 0.3345, "step": 423 }, { "epoch": 1.48, "learning_rate": 1.0605326876513318e-05, "loss": 0.3291, "step": 424 }, { "epoch": 1.48, "learning_rate": 1.0581113801452785e-05, "loss": 0.3667, "step": 425 }, { "epoch": 1.48, "learning_rate": 1.0556900726392252e-05, "loss": 0.3594, "step": 426 }, { "epoch": 1.49, "learning_rate": 1.0532687651331719e-05, "loss": 0.3579, "step": 427 }, { "epoch": 1.49, "learning_rate": 1.0508474576271188e-05, "loss": 0.3345, "step": 428 }, { "epoch": 1.49, "learning_rate": 1.0484261501210656e-05, "loss": 0.3281, "step": 429 }, { "epoch": 1.5, "learning_rate": 1.0460048426150122e-05, "loss": 0.3403, "step": 430 }, { "epoch": 1.5, "learning_rate": 1.043583535108959e-05, "loss": 0.3604, "step": 431 }, { "epoch": 1.51, "learning_rate": 1.0411622276029056e-05, "loss": 0.3335, "step": 432 }, { "epoch": 1.51, "learning_rate": 1.0387409200968524e-05, "loss": 0.3462, "step": 433 }, { "epoch": 1.51, "learning_rate": 1.036319612590799e-05, "loss": 0.3423, "step": 434 }, { "epoch": 1.52, "learning_rate": 1.0338983050847458e-05, "loss": 0.3364, "step": 435 }, { "epoch": 1.52, "learning_rate": 1.0314769975786927e-05, "loss": 0.3496, "step": 436 }, { "epoch": 1.52, "learning_rate": 1.0290556900726394e-05, "loss": 0.3325, "step": 437 }, { "epoch": 1.53, "learning_rate": 1.0266343825665861e-05, "loss": 0.3413, "step": 438 }, { "epoch": 1.53, "learning_rate": 1.0242130750605328e-05, "loss": 0.335, "step": 439 }, { "epoch": 1.53, "learning_rate": 1.0217917675544795e-05, "loss": 0.3423, "step": 440 }, { "epoch": 1.54, "learning_rate": 1.0193704600484262e-05, "loss": 0.3335, "step": 441 }, { "epoch": 1.54, "learning_rate": 1.016949152542373e-05, "loss": 0.3379, "step": 442 }, { "epoch": 1.54, "learning_rate": 1.0145278450363195e-05, "loss": 0.3506, "step": 443 }, { "epoch": 1.55, "learning_rate": 1.0121065375302663e-05, "loss": 0.3457, "step": 444 }, { "epoch": 1.55, "learning_rate": 1.0096852300242133e-05, "loss": 0.334, "step": 445 }, { "epoch": 1.55, "learning_rate": 1.0072639225181599e-05, "loss": 0.3408, "step": 446 }, { "epoch": 1.56, "learning_rate": 1.0048426150121067e-05, "loss": 0.3525, "step": 447 }, { "epoch": 1.56, "learning_rate": 1.0024213075060533e-05, "loss": 0.3491, "step": 448 }, { "epoch": 1.56, "learning_rate": 1e-05, "loss": 0.3286, "step": 449 }, { "epoch": 1.57, "learning_rate": 9.975786924939469e-06, "loss": 0.3159, "step": 450 }, { "epoch": 1.57, "learning_rate": 9.951573849878935e-06, "loss": 0.3252, "step": 451 }, { "epoch": 1.57, "learning_rate": 9.927360774818403e-06, "loss": 0.335, "step": 452 }, { "epoch": 1.58, "learning_rate": 9.90314769975787e-06, "loss": 0.3481, "step": 453 }, { "epoch": 1.58, "learning_rate": 9.878934624697337e-06, "loss": 0.3403, "step": 454 }, { "epoch": 1.59, "learning_rate": 9.854721549636804e-06, "loss": 0.3467, "step": 455 }, { "epoch": 1.59, "learning_rate": 9.830508474576272e-06, "loss": 0.3364, "step": 456 }, { "epoch": 1.59, "learning_rate": 9.80629539951574e-06, "loss": 0.3589, "step": 457 }, { "epoch": 1.6, "learning_rate": 9.782082324455206e-06, "loss": 0.3408, "step": 458 }, { "epoch": 1.6, "learning_rate": 9.757869249394674e-06, "loss": 0.3359, "step": 459 }, { "epoch": 1.6, "learning_rate": 9.733656174334142e-06, "loss": 0.3403, "step": 460 }, { "epoch": 1.61, "learning_rate": 9.709443099273608e-06, "loss": 0.3462, "step": 461 }, { "epoch": 1.61, "learning_rate": 9.685230024213076e-06, "loss": 0.3335, "step": 462 }, { "epoch": 1.61, "learning_rate": 9.661016949152544e-06, "loss": 0.3516, "step": 463 }, { "epoch": 1.62, "learning_rate": 9.63680387409201e-06, "loss": 0.3638, "step": 464 }, { "epoch": 1.62, "learning_rate": 9.612590799031478e-06, "loss": 0.3364, "step": 465 }, { "epoch": 1.62, "learning_rate": 9.588377723970946e-06, "loss": 0.3364, "step": 466 }, { "epoch": 1.63, "learning_rate": 9.564164648910412e-06, "loss": 0.3496, "step": 467 }, { "epoch": 1.63, "learning_rate": 9.53995157384988e-06, "loss": 0.3403, "step": 468 }, { "epoch": 1.63, "learning_rate": 9.515738498789347e-06, "loss": 0.3481, "step": 469 }, { "epoch": 1.64, "learning_rate": 9.491525423728815e-06, "loss": 0.3374, "step": 470 }, { "epoch": 1.64, "learning_rate": 9.467312348668281e-06, "loss": 0.3174, "step": 471 }, { "epoch": 1.64, "learning_rate": 9.44309927360775e-06, "loss": 0.3633, "step": 472 }, { "epoch": 1.65, "learning_rate": 9.418886198547215e-06, "loss": 0.3472, "step": 473 }, { "epoch": 1.65, "learning_rate": 9.394673123486683e-06, "loss": 0.3379, "step": 474 }, { "epoch": 1.66, "learning_rate": 9.370460048426151e-06, "loss": 0.3428, "step": 475 }, { "epoch": 1.66, "learning_rate": 9.346246973365619e-06, "loss": 0.3369, "step": 476 }, { "epoch": 1.66, "learning_rate": 9.322033898305085e-06, "loss": 0.354, "step": 477 }, { "epoch": 1.67, "learning_rate": 9.297820823244553e-06, "loss": 0.3467, "step": 478 }, { "epoch": 1.67, "learning_rate": 9.27360774818402e-06, "loss": 0.3379, "step": 479 }, { "epoch": 1.67, "learning_rate": 9.249394673123487e-06, "loss": 0.3584, "step": 480 }, { "epoch": 1.68, "learning_rate": 9.225181598062955e-06, "loss": 0.3335, "step": 481 }, { "epoch": 1.68, "learning_rate": 9.200968523002422e-06, "loss": 0.3247, "step": 482 }, { "epoch": 1.68, "learning_rate": 9.17675544794189e-06, "loss": 0.3403, "step": 483 }, { "epoch": 1.69, "learning_rate": 9.152542372881356e-06, "loss": 0.3442, "step": 484 }, { "epoch": 1.69, "learning_rate": 9.128329297820824e-06, "loss": 0.334, "step": 485 }, { "epoch": 1.69, "learning_rate": 9.10411622276029e-06, "loss": 0.3369, "step": 486 }, { "epoch": 1.7, "learning_rate": 9.079903147699758e-06, "loss": 0.3496, "step": 487 }, { "epoch": 1.7, "learning_rate": 9.055690072639226e-06, "loss": 0.3477, "step": 488 }, { "epoch": 1.7, "learning_rate": 9.031476997578694e-06, "loss": 0.3447, "step": 489 }, { "epoch": 1.71, "learning_rate": 9.00726392251816e-06, "loss": 0.3286, "step": 490 }, { "epoch": 1.71, "learning_rate": 8.983050847457628e-06, "loss": 0.3306, "step": 491 }, { "epoch": 1.71, "learning_rate": 8.958837772397096e-06, "loss": 0.3379, "step": 492 }, { "epoch": 1.72, "learning_rate": 8.934624697336562e-06, "loss": 0.3257, "step": 493 }, { "epoch": 1.72, "learning_rate": 8.91041162227603e-06, "loss": 0.3447, "step": 494 }, { "epoch": 1.72, "learning_rate": 8.886198547215496e-06, "loss": 0.3237, "step": 495 }, { "epoch": 1.73, "learning_rate": 8.861985472154965e-06, "loss": 0.3296, "step": 496 }, { "epoch": 1.73, "learning_rate": 8.837772397094432e-06, "loss": 0.3452, "step": 497 }, { "epoch": 1.74, "learning_rate": 8.8135593220339e-06, "loss": 0.3257, "step": 498 }, { "epoch": 1.74, "learning_rate": 8.789346246973365e-06, "loss": 0.353, "step": 499 }, { "epoch": 1.74, "learning_rate": 8.765133171912833e-06, "loss": 0.3345, "step": 500 }, { "epoch": 1.75, "learning_rate": 8.740920096852301e-06, "loss": 0.3374, "step": 501 }, { "epoch": 1.75, "learning_rate": 8.716707021791769e-06, "loss": 0.3418, "step": 502 }, { "epoch": 1.75, "learning_rate": 8.692493946731235e-06, "loss": 0.3481, "step": 503 }, { "epoch": 1.76, "learning_rate": 8.668280871670703e-06, "loss": 0.3389, "step": 504 }, { "epoch": 1.76, "learning_rate": 8.64406779661017e-06, "loss": 0.3413, "step": 505 }, { "epoch": 1.76, "learning_rate": 8.619854721549637e-06, "loss": 0.3438, "step": 506 }, { "epoch": 1.77, "learning_rate": 8.595641646489105e-06, "loss": 0.332, "step": 507 }, { "epoch": 1.77, "learning_rate": 8.571428571428571e-06, "loss": 0.3687, "step": 508 }, { "epoch": 1.77, "learning_rate": 8.54721549636804e-06, "loss": 0.3315, "step": 509 }, { "epoch": 1.78, "learning_rate": 8.523002421307507e-06, "loss": 0.3442, "step": 510 }, { "epoch": 1.78, "learning_rate": 8.498789346246974e-06, "loss": 0.3467, "step": 511 }, { "epoch": 1.78, "learning_rate": 8.47457627118644e-06, "loss": 0.3325, "step": 512 }, { "epoch": 1.79, "learning_rate": 8.450363196125908e-06, "loss": 0.3213, "step": 513 }, { "epoch": 1.79, "learning_rate": 8.426150121065376e-06, "loss": 0.3325, "step": 514 }, { "epoch": 1.79, "learning_rate": 8.401937046004844e-06, "loss": 0.334, "step": 515 }, { "epoch": 1.8, "learning_rate": 8.37772397094431e-06, "loss": 0.3418, "step": 516 }, { "epoch": 1.8, "learning_rate": 8.353510895883778e-06, "loss": 0.3311, "step": 517 }, { "epoch": 1.8, "learning_rate": 8.329297820823246e-06, "loss": 0.3394, "step": 518 }, { "epoch": 1.81, "learning_rate": 8.305084745762712e-06, "loss": 0.3306, "step": 519 }, { "epoch": 1.81, "learning_rate": 8.28087167070218e-06, "loss": 0.3506, "step": 520 }, { "epoch": 1.82, "learning_rate": 8.256658595641646e-06, "loss": 0.3291, "step": 521 }, { "epoch": 1.82, "learning_rate": 8.232445520581116e-06, "loss": 0.353, "step": 522 }, { "epoch": 1.82, "learning_rate": 8.208232445520582e-06, "loss": 0.354, "step": 523 }, { "epoch": 1.83, "learning_rate": 8.18401937046005e-06, "loss": 0.3364, "step": 524 }, { "epoch": 1.83, "learning_rate": 8.159806295399516e-06, "loss": 0.3394, "step": 525 }, { "epoch": 1.83, "learning_rate": 8.135593220338983e-06, "loss": 0.3457, "step": 526 }, { "epoch": 1.84, "learning_rate": 8.111380145278451e-06, "loss": 0.3296, "step": 527 }, { "epoch": 1.84, "learning_rate": 8.08716707021792e-06, "loss": 0.3569, "step": 528 }, { "epoch": 1.84, "learning_rate": 8.062953995157385e-06, "loss": 0.3389, "step": 529 }, { "epoch": 1.85, "learning_rate": 8.038740920096853e-06, "loss": 0.3394, "step": 530 }, { "epoch": 1.85, "learning_rate": 8.014527845036321e-06, "loss": 0.3364, "step": 531 }, { "epoch": 1.85, "learning_rate": 7.990314769975787e-06, "loss": 0.3467, "step": 532 }, { "epoch": 1.86, "learning_rate": 7.966101694915255e-06, "loss": 0.3462, "step": 533 }, { "epoch": 1.86, "learning_rate": 7.941888619854721e-06, "loss": 0.334, "step": 534 }, { "epoch": 1.86, "learning_rate": 7.91767554479419e-06, "loss": 0.3501, "step": 535 }, { "epoch": 1.87, "learning_rate": 7.893462469733657e-06, "loss": 0.3296, "step": 536 }, { "epoch": 1.87, "learning_rate": 7.869249394673125e-06, "loss": 0.3438, "step": 537 }, { "epoch": 1.87, "learning_rate": 7.84503631961259e-06, "loss": 0.3306, "step": 538 }, { "epoch": 1.88, "learning_rate": 7.820823244552059e-06, "loss": 0.3491, "step": 539 }, { "epoch": 1.88, "learning_rate": 7.796610169491526e-06, "loss": 0.3286, "step": 540 }, { "epoch": 1.89, "learning_rate": 7.772397094430994e-06, "loss": 0.356, "step": 541 }, { "epoch": 1.89, "learning_rate": 7.74818401937046e-06, "loss": 0.3535, "step": 542 }, { "epoch": 1.89, "learning_rate": 7.723970944309928e-06, "loss": 0.3345, "step": 543 }, { "epoch": 1.9, "learning_rate": 7.699757869249396e-06, "loss": 0.3398, "step": 544 }, { "epoch": 1.9, "learning_rate": 7.675544794188862e-06, "loss": 0.3296, "step": 545 }, { "epoch": 1.9, "learning_rate": 7.65133171912833e-06, "loss": 0.3496, "step": 546 }, { "epoch": 1.91, "learning_rate": 7.627118644067797e-06, "loss": 0.3301, "step": 547 }, { "epoch": 1.91, "learning_rate": 7.602905569007265e-06, "loss": 0.3574, "step": 548 }, { "epoch": 1.91, "learning_rate": 7.578692493946732e-06, "loss": 0.3418, "step": 549 }, { "epoch": 1.92, "learning_rate": 7.554479418886199e-06, "loss": 0.3398, "step": 550 }, { "epoch": 1.92, "learning_rate": 7.530266343825666e-06, "loss": 0.354, "step": 551 }, { "epoch": 1.92, "learning_rate": 7.506053268765134e-06, "loss": 0.3247, "step": 552 }, { "epoch": 1.93, "learning_rate": 7.4818401937046015e-06, "loss": 0.353, "step": 553 }, { "epoch": 1.93, "learning_rate": 7.4576271186440685e-06, "loss": 0.3359, "step": 554 }, { "epoch": 1.93, "learning_rate": 7.4334140435835355e-06, "loss": 0.3535, "step": 555 }, { "epoch": 1.94, "learning_rate": 7.4092009685230025e-06, "loss": 0.3276, "step": 556 }, { "epoch": 1.94, "learning_rate": 7.384987893462471e-06, "loss": 0.3457, "step": 557 }, { "epoch": 1.94, "learning_rate": 7.360774818401938e-06, "loss": 0.3423, "step": 558 }, { "epoch": 1.95, "learning_rate": 7.336561743341405e-06, "loss": 0.3408, "step": 559 }, { "epoch": 1.95, "learning_rate": 7.312348668280872e-06, "loss": 0.3467, "step": 560 }, { "epoch": 1.95, "learning_rate": 7.288135593220339e-06, "loss": 0.3291, "step": 561 }, { "epoch": 1.96, "learning_rate": 7.263922518159807e-06, "loss": 0.3423, "step": 562 }, { "epoch": 1.96, "learning_rate": 7.239709443099274e-06, "loss": 0.3325, "step": 563 }, { "epoch": 1.97, "learning_rate": 7.215496368038741e-06, "loss": 0.3413, "step": 564 }, { "epoch": 1.97, "learning_rate": 7.191283292978209e-06, "loss": 0.3472, "step": 565 }, { "epoch": 1.97, "learning_rate": 7.1670702179176766e-06, "loss": 0.3462, "step": 566 }, { "epoch": 1.98, "learning_rate": 7.1428571428571436e-06, "loss": 0.3394, "step": 567 }, { "epoch": 1.98, "learning_rate": 7.1186440677966106e-06, "loss": 0.3315, "step": 568 }, { "epoch": 1.98, "learning_rate": 7.0944309927360775e-06, "loss": 0.3496, "step": 569 }, { "epoch": 1.99, "learning_rate": 7.070217917675546e-06, "loss": 0.3638, "step": 570 }, { "epoch": 1.99, "learning_rate": 7.046004842615013e-06, "loss": 0.3408, "step": 571 }, { "epoch": 1.99, "learning_rate": 7.02179176755448e-06, "loss": 0.3457, "step": 572 }, { "epoch": 2.0, "learning_rate": 6.997578692493947e-06, "loss": 0.3374, "step": 573 }, { "epoch": 2.0, "learning_rate": 6.973365617433414e-06, "loss": 0.2184, "step": 574 }, { "epoch": 2.0, "learning_rate": 6.949152542372882e-06, "loss": 0.1985, "step": 575 }, { "epoch": 2.01, "learning_rate": 6.924939467312349e-06, "loss": 0.2029, "step": 576 }, { "epoch": 2.01, "learning_rate": 6.900726392251816e-06, "loss": 0.1963, "step": 577 }, { "epoch": 2.01, "learning_rate": 6.876513317191284e-06, "loss": 0.2009, "step": 578 }, { "epoch": 2.02, "learning_rate": 6.852300242130752e-06, "loss": 0.1885, "step": 579 }, { "epoch": 2.02, "learning_rate": 6.828087167070219e-06, "loss": 0.1909, "step": 580 }, { "epoch": 2.02, "learning_rate": 6.803874092009686e-06, "loss": 0.1858, "step": 581 }, { "epoch": 2.03, "learning_rate": 6.779661016949153e-06, "loss": 0.1929, "step": 582 }, { "epoch": 2.03, "learning_rate": 6.75544794188862e-06, "loss": 0.1863, "step": 583 }, { "epoch": 2.03, "learning_rate": 6.731234866828088e-06, "loss": 0.1941, "step": 584 }, { "epoch": 2.04, "learning_rate": 6.707021791767555e-06, "loss": 0.1946, "step": 585 }, { "epoch": 2.04, "learning_rate": 6.682808716707022e-06, "loss": 0.198, "step": 586 }, { "epoch": 2.05, "learning_rate": 6.658595641646489e-06, "loss": 0.1833, "step": 587 }, { "epoch": 2.05, "learning_rate": 6.634382566585957e-06, "loss": 0.1975, "step": 588 }, { "epoch": 2.05, "learning_rate": 6.610169491525424e-06, "loss": 0.1831, "step": 589 }, { "epoch": 2.06, "learning_rate": 6.585956416464891e-06, "loss": 0.1826, "step": 590 }, { "epoch": 2.06, "learning_rate": 6.561743341404359e-06, "loss": 0.188, "step": 591 }, { "epoch": 2.06, "learning_rate": 6.537530266343827e-06, "loss": 0.1812, "step": 592 }, { "epoch": 2.07, "learning_rate": 6.513317191283294e-06, "loss": 0.1882, "step": 593 }, { "epoch": 2.07, "learning_rate": 6.489104116222761e-06, "loss": 0.1992, "step": 594 }, { "epoch": 2.07, "learning_rate": 6.464891041162228e-06, "loss": 0.1919, "step": 595 }, { "epoch": 2.08, "learning_rate": 6.440677966101695e-06, "loss": 0.1775, "step": 596 }, { "epoch": 2.08, "learning_rate": 6.416464891041163e-06, "loss": 0.1812, "step": 597 }, { "epoch": 2.08, "learning_rate": 6.39225181598063e-06, "loss": 0.1824, "step": 598 }, { "epoch": 2.09, "learning_rate": 6.368038740920097e-06, "loss": 0.1648, "step": 599 }, { "epoch": 2.09, "learning_rate": 6.343825665859564e-06, "loss": 0.1882, "step": 600 }, { "epoch": 2.09, "learning_rate": 6.319612590799032e-06, "loss": 0.1824, "step": 601 }, { "epoch": 2.1, "learning_rate": 6.295399515738499e-06, "loss": 0.179, "step": 602 }, { "epoch": 2.1, "learning_rate": 6.271186440677966e-06, "loss": 0.1785, "step": 603 }, { "epoch": 2.1, "learning_rate": 6.246973365617434e-06, "loss": 0.1843, "step": 604 }, { "epoch": 2.11, "learning_rate": 6.222760290556902e-06, "loss": 0.1995, "step": 605 }, { "epoch": 2.11, "learning_rate": 6.198547215496369e-06, "loss": 0.179, "step": 606 }, { "epoch": 2.11, "learning_rate": 6.174334140435836e-06, "loss": 0.1758, "step": 607 }, { "epoch": 2.12, "learning_rate": 6.150121065375303e-06, "loss": 0.1804, "step": 608 }, { "epoch": 2.12, "learning_rate": 6.12590799031477e-06, "loss": 0.1895, "step": 609 }, { "epoch": 2.13, "learning_rate": 6.1016949152542385e-06, "loss": 0.1841, "step": 610 }, { "epoch": 2.13, "learning_rate": 6.0774818401937055e-06, "loss": 0.1719, "step": 611 }, { "epoch": 2.13, "learning_rate": 6.0532687651331724e-06, "loss": 0.1838, "step": 612 }, { "epoch": 2.14, "learning_rate": 6.0290556900726394e-06, "loss": 0.179, "step": 613 }, { "epoch": 2.14, "learning_rate": 6.004842615012107e-06, "loss": 0.1711, "step": 614 }, { "epoch": 2.14, "learning_rate": 5.980629539951574e-06, "loss": 0.1777, "step": 615 }, { "epoch": 2.15, "learning_rate": 5.956416464891041e-06, "loss": 0.1643, "step": 616 }, { "epoch": 2.15, "learning_rate": 5.932203389830509e-06, "loss": 0.177, "step": 617 }, { "epoch": 2.15, "learning_rate": 5.907990314769976e-06, "loss": 0.1804, "step": 618 }, { "epoch": 2.16, "learning_rate": 5.883777239709444e-06, "loss": 0.187, "step": 619 }, { "epoch": 2.16, "learning_rate": 5.859564164648911e-06, "loss": 0.1609, "step": 620 }, { "epoch": 2.16, "learning_rate": 5.835351089588378e-06, "loss": 0.1819, "step": 621 }, { "epoch": 2.17, "learning_rate": 5.811138014527845e-06, "loss": 0.1743, "step": 622 }, { "epoch": 2.17, "learning_rate": 5.7869249394673135e-06, "loss": 0.1711, "step": 623 }, { "epoch": 2.17, "learning_rate": 5.7627118644067805e-06, "loss": 0.1799, "step": 624 }, { "epoch": 2.18, "learning_rate": 5.7384987893462475e-06, "loss": 0.1843, "step": 625 }, { "epoch": 2.18, "learning_rate": 5.7142857142857145e-06, "loss": 0.1768, "step": 626 }, { "epoch": 2.18, "learning_rate": 5.690072639225182e-06, "loss": 0.1804, "step": 627 }, { "epoch": 2.19, "learning_rate": 5.665859564164649e-06, "loss": 0.1653, "step": 628 }, { "epoch": 2.19, "learning_rate": 5.641646489104116e-06, "loss": 0.1763, "step": 629 }, { "epoch": 2.2, "learning_rate": 5.617433414043584e-06, "loss": 0.1841, "step": 630 }, { "epoch": 2.2, "learning_rate": 5.593220338983051e-06, "loss": 0.1792, "step": 631 }, { "epoch": 2.2, "learning_rate": 5.569007263922519e-06, "loss": 0.1631, "step": 632 }, { "epoch": 2.21, "learning_rate": 5.544794188861986e-06, "loss": 0.178, "step": 633 }, { "epoch": 2.21, "learning_rate": 5.520581113801453e-06, "loss": 0.1785, "step": 634 }, { "epoch": 2.21, "learning_rate": 5.49636803874092e-06, "loss": 0.1682, "step": 635 }, { "epoch": 2.22, "learning_rate": 5.472154963680389e-06, "loss": 0.1768, "step": 636 }, { "epoch": 2.22, "learning_rate": 5.447941888619856e-06, "loss": 0.178, "step": 637 }, { "epoch": 2.22, "learning_rate": 5.423728813559323e-06, "loss": 0.1777, "step": 638 }, { "epoch": 2.23, "learning_rate": 5.39951573849879e-06, "loss": 0.176, "step": 639 }, { "epoch": 2.23, "learning_rate": 5.375302663438257e-06, "loss": 0.178, "step": 640 }, { "epoch": 2.23, "learning_rate": 5.351089588377724e-06, "loss": 0.1628, "step": 641 }, { "epoch": 2.24, "learning_rate": 5.326876513317191e-06, "loss": 0.1719, "step": 642 }, { "epoch": 2.24, "learning_rate": 5.302663438256659e-06, "loss": 0.1687, "step": 643 }, { "epoch": 2.24, "learning_rate": 5.278450363196126e-06, "loss": 0.1819, "step": 644 }, { "epoch": 2.25, "learning_rate": 5.254237288135594e-06, "loss": 0.1741, "step": 645 }, { "epoch": 2.25, "learning_rate": 5.230024213075061e-06, "loss": 0.168, "step": 646 }, { "epoch": 2.25, "learning_rate": 5.205811138014528e-06, "loss": 0.1782, "step": 647 }, { "epoch": 2.26, "learning_rate": 5.181598062953995e-06, "loss": 0.1829, "step": 648 }, { "epoch": 2.26, "learning_rate": 5.157384987893464e-06, "loss": 0.1807, "step": 649 }, { "epoch": 2.26, "learning_rate": 5.133171912832931e-06, "loss": 0.1775, "step": 650 }, { "epoch": 2.27, "learning_rate": 5.108958837772398e-06, "loss": 0.1865, "step": 651 }, { "epoch": 2.27, "learning_rate": 5.084745762711865e-06, "loss": 0.1792, "step": 652 }, { "epoch": 2.28, "learning_rate": 5.060532687651332e-06, "loss": 0.1807, "step": 653 }, { "epoch": 2.28, "learning_rate": 5.0363196125907995e-06, "loss": 0.1768, "step": 654 }, { "epoch": 2.28, "learning_rate": 5.0121065375302665e-06, "loss": 0.1714, "step": 655 }, { "epoch": 2.29, "learning_rate": 4.987893462469734e-06, "loss": 0.1758, "step": 656 }, { "epoch": 2.29, "learning_rate": 4.963680387409201e-06, "loss": 0.1794, "step": 657 }, { "epoch": 2.29, "learning_rate": 4.939467312348668e-06, "loss": 0.1794, "step": 658 }, { "epoch": 2.3, "learning_rate": 4.915254237288136e-06, "loss": 0.1677, "step": 659 }, { "epoch": 2.3, "learning_rate": 4.891041162227603e-06, "loss": 0.1672, "step": 660 }, { "epoch": 2.3, "learning_rate": 4.866828087167071e-06, "loss": 0.1807, "step": 661 }, { "epoch": 2.31, "learning_rate": 4.842615012106538e-06, "loss": 0.1731, "step": 662 }, { "epoch": 2.31, "learning_rate": 4.818401937046005e-06, "loss": 0.1721, "step": 663 }, { "epoch": 2.31, "learning_rate": 4.794188861985473e-06, "loss": 0.1724, "step": 664 }, { "epoch": 2.32, "learning_rate": 4.76997578692494e-06, "loss": 0.1711, "step": 665 }, { "epoch": 2.32, "learning_rate": 4.745762711864408e-06, "loss": 0.1826, "step": 666 }, { "epoch": 2.32, "learning_rate": 4.721549636803875e-06, "loss": 0.1907, "step": 667 }, { "epoch": 2.33, "learning_rate": 4.6973365617433416e-06, "loss": 0.1743, "step": 668 }, { "epoch": 2.33, "learning_rate": 4.673123486682809e-06, "loss": 0.1602, "step": 669 }, { "epoch": 2.33, "learning_rate": 4.648910411622276e-06, "loss": 0.1702, "step": 670 }, { "epoch": 2.34, "learning_rate": 4.624697336561743e-06, "loss": 0.1914, "step": 671 }, { "epoch": 2.34, "learning_rate": 4.600484261501211e-06, "loss": 0.1677, "step": 672 }, { "epoch": 2.34, "learning_rate": 4.576271186440678e-06, "loss": 0.1775, "step": 673 }, { "epoch": 2.35, "learning_rate": 4.552058111380145e-06, "loss": 0.1685, "step": 674 }, { "epoch": 2.35, "learning_rate": 4.527845036319613e-06, "loss": 0.1709, "step": 675 }, { "epoch": 2.36, "learning_rate": 4.50363196125908e-06, "loss": 0.1743, "step": 676 }, { "epoch": 2.36, "learning_rate": 4.479418886198548e-06, "loss": 0.1753, "step": 677 }, { "epoch": 2.36, "learning_rate": 4.455205811138015e-06, "loss": 0.1685, "step": 678 }, { "epoch": 2.37, "learning_rate": 4.430992736077483e-06, "loss": 0.1746, "step": 679 }, { "epoch": 2.37, "learning_rate": 4.40677966101695e-06, "loss": 0.1851, "step": 680 }, { "epoch": 2.37, "learning_rate": 4.382566585956417e-06, "loss": 0.179, "step": 681 }, { "epoch": 2.38, "learning_rate": 4.3583535108958845e-06, "loss": 0.1853, "step": 682 }, { "epoch": 2.38, "learning_rate": 4.3341404358353515e-06, "loss": 0.1721, "step": 683 }, { "epoch": 2.38, "learning_rate": 4.3099273607748185e-06, "loss": 0.1702, "step": 684 }, { "epoch": 2.39, "learning_rate": 4.2857142857142855e-06, "loss": 0.1636, "step": 685 }, { "epoch": 2.39, "learning_rate": 4.261501210653753e-06, "loss": 0.1816, "step": 686 }, { "epoch": 2.39, "learning_rate": 4.23728813559322e-06, "loss": 0.1741, "step": 687 }, { "epoch": 2.4, "learning_rate": 4.213075060532688e-06, "loss": 0.1765, "step": 688 }, { "epoch": 2.4, "learning_rate": 4.188861985472155e-06, "loss": 0.1731, "step": 689 }, { "epoch": 2.4, "learning_rate": 4.164648910411623e-06, "loss": 0.1782, "step": 690 }, { "epoch": 2.41, "learning_rate": 4.14043583535109e-06, "loss": 0.1709, "step": 691 }, { "epoch": 2.41, "learning_rate": 4.116222760290558e-06, "loss": 0.1758, "step": 692 }, { "epoch": 2.41, "learning_rate": 4.092009685230025e-06, "loss": 0.1719, "step": 693 }, { "epoch": 2.42, "learning_rate": 4.067796610169492e-06, "loss": 0.1741, "step": 694 }, { "epoch": 2.42, "learning_rate": 4.04358353510896e-06, "loss": 0.1731, "step": 695 }, { "epoch": 2.43, "learning_rate": 4.0193704600484266e-06, "loss": 0.1699, "step": 696 }, { "epoch": 2.43, "learning_rate": 3.9951573849878936e-06, "loss": 0.178, "step": 697 }, { "epoch": 2.43, "learning_rate": 3.9709443099273605e-06, "loss": 0.1807, "step": 698 }, { "epoch": 2.44, "learning_rate": 3.946731234866828e-06, "loss": 0.1711, "step": 699 }, { "epoch": 2.44, "learning_rate": 3.922518159806295e-06, "loss": 0.1765, "step": 700 }, { "epoch": 2.44, "learning_rate": 3.898305084745763e-06, "loss": 0.1743, "step": 701 }, { "epoch": 2.45, "learning_rate": 3.87409200968523e-06, "loss": 0.1719, "step": 702 }, { "epoch": 2.45, "learning_rate": 3.849878934624698e-06, "loss": 0.175, "step": 703 }, { "epoch": 2.45, "learning_rate": 3.825665859564165e-06, "loss": 0.1816, "step": 704 }, { "epoch": 2.46, "learning_rate": 3.8014527845036324e-06, "loss": 0.165, "step": 705 }, { "epoch": 2.46, "learning_rate": 3.7772397094430994e-06, "loss": 0.177, "step": 706 }, { "epoch": 2.46, "learning_rate": 3.753026634382567e-06, "loss": 0.1829, "step": 707 }, { "epoch": 2.47, "learning_rate": 3.7288135593220342e-06, "loss": 0.179, "step": 708 }, { "epoch": 2.47, "learning_rate": 3.7046004842615012e-06, "loss": 0.177, "step": 709 }, { "epoch": 2.47, "learning_rate": 3.680387409200969e-06, "loss": 0.1821, "step": 710 }, { "epoch": 2.48, "learning_rate": 3.656174334140436e-06, "loss": 0.1733, "step": 711 }, { "epoch": 2.48, "learning_rate": 3.6319612590799035e-06, "loss": 0.1792, "step": 712 }, { "epoch": 2.48, "learning_rate": 3.6077481840193705e-06, "loss": 0.1785, "step": 713 }, { "epoch": 2.49, "learning_rate": 3.5835351089588383e-06, "loss": 0.1638, "step": 714 }, { "epoch": 2.49, "learning_rate": 3.5593220338983053e-06, "loss": 0.1643, "step": 715 }, { "epoch": 2.49, "learning_rate": 3.535108958837773e-06, "loss": 0.1775, "step": 716 }, { "epoch": 2.5, "learning_rate": 3.51089588377724e-06, "loss": 0.1614, "step": 717 }, { "epoch": 2.5, "learning_rate": 3.486682808716707e-06, "loss": 0.186, "step": 718 }, { "epoch": 2.51, "learning_rate": 3.4624697336561745e-06, "loss": 0.1772, "step": 719 }, { "epoch": 2.51, "learning_rate": 3.438256658595642e-06, "loss": 0.1729, "step": 720 }, { "epoch": 2.51, "learning_rate": 3.4140435835351093e-06, "loss": 0.176, "step": 721 }, { "epoch": 2.52, "learning_rate": 3.3898305084745763e-06, "loss": 0.1738, "step": 722 }, { "epoch": 2.52, "learning_rate": 3.365617433414044e-06, "loss": 0.1626, "step": 723 }, { "epoch": 2.52, "learning_rate": 3.341404358353511e-06, "loss": 0.1792, "step": 724 }, { "epoch": 2.53, "learning_rate": 3.3171912832929785e-06, "loss": 0.1621, "step": 725 }, { "epoch": 2.53, "learning_rate": 3.2929782082324455e-06, "loss": 0.1802, "step": 726 }, { "epoch": 2.53, "learning_rate": 3.2687651331719134e-06, "loss": 0.1675, "step": 727 }, { "epoch": 2.54, "learning_rate": 3.2445520581113804e-06, "loss": 0.1729, "step": 728 }, { "epoch": 2.54, "learning_rate": 3.2203389830508473e-06, "loss": 0.1748, "step": 729 }, { "epoch": 2.54, "learning_rate": 3.196125907990315e-06, "loss": 0.1716, "step": 730 }, { "epoch": 2.55, "learning_rate": 3.171912832929782e-06, "loss": 0.1699, "step": 731 }, { "epoch": 2.55, "learning_rate": 3.1476997578692496e-06, "loss": 0.1841, "step": 732 }, { "epoch": 2.55, "learning_rate": 3.123486682808717e-06, "loss": 0.1943, "step": 733 }, { "epoch": 2.56, "learning_rate": 3.0992736077481844e-06, "loss": 0.1865, "step": 734 }, { "epoch": 2.56, "learning_rate": 3.0750605326876514e-06, "loss": 0.168, "step": 735 }, { "epoch": 2.56, "learning_rate": 3.0508474576271192e-06, "loss": 0.1768, "step": 736 }, { "epoch": 2.57, "learning_rate": 3.0266343825665862e-06, "loss": 0.1689, "step": 737 }, { "epoch": 2.57, "learning_rate": 3.0024213075060536e-06, "loss": 0.1753, "step": 738 }, { "epoch": 2.57, "learning_rate": 2.9782082324455206e-06, "loss": 0.1672, "step": 739 }, { "epoch": 2.58, "learning_rate": 2.953995157384988e-06, "loss": 0.1831, "step": 740 }, { "epoch": 2.58, "learning_rate": 2.9297820823244554e-06, "loss": 0.1697, "step": 741 }, { "epoch": 2.59, "learning_rate": 2.9055690072639224e-06, "loss": 0.1626, "step": 742 }, { "epoch": 2.59, "learning_rate": 2.8813559322033903e-06, "loss": 0.176, "step": 743 }, { "epoch": 2.59, "learning_rate": 2.8571428571428573e-06, "loss": 0.1785, "step": 744 }, { "epoch": 2.6, "learning_rate": 2.8329297820823247e-06, "loss": 0.1716, "step": 745 }, { "epoch": 2.6, "learning_rate": 2.808716707021792e-06, "loss": 0.1831, "step": 746 }, { "epoch": 2.6, "learning_rate": 2.7845036319612595e-06, "loss": 0.1721, "step": 747 }, { "epoch": 2.61, "learning_rate": 2.7602905569007265e-06, "loss": 0.1829, "step": 748 }, { "epoch": 2.61, "learning_rate": 2.7360774818401943e-06, "loss": 0.167, "step": 749 }, { "epoch": 2.61, "learning_rate": 2.7118644067796613e-06, "loss": 0.1804, "step": 750 }, { "epoch": 2.62, "learning_rate": 2.6876513317191283e-06, "loss": 0.179, "step": 751 }, { "epoch": 2.62, "learning_rate": 2.6634382566585957e-06, "loss": 0.1851, "step": 752 }, { "epoch": 2.62, "learning_rate": 2.639225181598063e-06, "loss": 0.1699, "step": 753 }, { "epoch": 2.63, "learning_rate": 2.6150121065375305e-06, "loss": 0.1743, "step": 754 }, { "epoch": 2.63, "learning_rate": 2.5907990314769975e-06, "loss": 0.1763, "step": 755 }, { "epoch": 2.63, "learning_rate": 2.5665859564164654e-06, "loss": 0.1719, "step": 756 }, { "epoch": 2.64, "learning_rate": 2.5423728813559323e-06, "loss": 0.1743, "step": 757 }, { "epoch": 2.64, "learning_rate": 2.5181598062953998e-06, "loss": 0.1714, "step": 758 }, { "epoch": 2.64, "learning_rate": 2.493946731234867e-06, "loss": 0.1689, "step": 759 }, { "epoch": 2.65, "learning_rate": 2.469733656174334e-06, "loss": 0.1753, "step": 760 }, { "epoch": 2.65, "learning_rate": 2.4455205811138016e-06, "loss": 0.1741, "step": 761 }, { "epoch": 2.66, "learning_rate": 2.421307506053269e-06, "loss": 0.1711, "step": 762 }, { "epoch": 2.66, "learning_rate": 2.3970944309927364e-06, "loss": 0.1692, "step": 763 }, { "epoch": 2.66, "learning_rate": 2.372881355932204e-06, "loss": 0.1692, "step": 764 }, { "epoch": 2.67, "learning_rate": 2.3486682808716708e-06, "loss": 0.1729, "step": 765 }, { "epoch": 2.67, "learning_rate": 2.324455205811138e-06, "loss": 0.1804, "step": 766 }, { "epoch": 2.67, "learning_rate": 2.3002421307506056e-06, "loss": 0.1729, "step": 767 }, { "epoch": 2.68, "learning_rate": 2.2760290556900726e-06, "loss": 0.1897, "step": 768 }, { "epoch": 2.68, "learning_rate": 2.25181598062954e-06, "loss": 0.1711, "step": 769 }, { "epoch": 2.68, "learning_rate": 2.2276029055690074e-06, "loss": 0.1726, "step": 770 }, { "epoch": 2.69, "learning_rate": 2.203389830508475e-06, "loss": 0.1794, "step": 771 }, { "epoch": 2.69, "learning_rate": 2.1791767554479422e-06, "loss": 0.1721, "step": 772 }, { "epoch": 2.69, "learning_rate": 2.1549636803874092e-06, "loss": 0.1624, "step": 773 }, { "epoch": 2.7, "learning_rate": 2.1307506053268766e-06, "loss": 0.187, "step": 774 }, { "epoch": 2.7, "learning_rate": 2.106537530266344e-06, "loss": 0.1794, "step": 775 }, { "epoch": 2.7, "learning_rate": 2.0823244552058115e-06, "loss": 0.1689, "step": 776 }, { "epoch": 2.71, "learning_rate": 2.058111380145279e-06, "loss": 0.1614, "step": 777 }, { "epoch": 2.71, "learning_rate": 2.033898305084746e-06, "loss": 0.1846, "step": 778 }, { "epoch": 2.71, "learning_rate": 2.0096852300242133e-06, "loss": 0.1611, "step": 779 }, { "epoch": 2.72, "learning_rate": 1.9854721549636803e-06, "loss": 0.1599, "step": 780 }, { "epoch": 2.72, "learning_rate": 1.9612590799031477e-06, "loss": 0.1733, "step": 781 }, { "epoch": 2.72, "learning_rate": 1.937046004842615e-06, "loss": 0.1794, "step": 782 }, { "epoch": 2.73, "learning_rate": 1.9128329297820825e-06, "loss": 0.1782, "step": 783 }, { "epoch": 2.73, "learning_rate": 1.8886198547215497e-06, "loss": 0.1658, "step": 784 }, { "epoch": 2.74, "learning_rate": 1.8644067796610171e-06, "loss": 0.179, "step": 785 }, { "epoch": 2.74, "learning_rate": 1.8401937046004845e-06, "loss": 0.1738, "step": 786 }, { "epoch": 2.74, "learning_rate": 1.8159806295399517e-06, "loss": 0.1575, "step": 787 }, { "epoch": 2.75, "learning_rate": 1.7917675544794191e-06, "loss": 0.1677, "step": 788 }, { "epoch": 2.75, "learning_rate": 1.7675544794188866e-06, "loss": 0.1699, "step": 789 }, { "epoch": 2.75, "learning_rate": 1.7433414043583535e-06, "loss": 0.177, "step": 790 }, { "epoch": 2.76, "learning_rate": 1.719128329297821e-06, "loss": 0.1982, "step": 791 }, { "epoch": 2.76, "learning_rate": 1.6949152542372882e-06, "loss": 0.1599, "step": 792 }, { "epoch": 2.76, "learning_rate": 1.6707021791767556e-06, "loss": 0.1724, "step": 793 }, { "epoch": 2.77, "learning_rate": 1.6464891041162228e-06, "loss": 0.1694, "step": 794 }, { "epoch": 2.77, "learning_rate": 1.6222760290556902e-06, "loss": 0.1733, "step": 795 }, { "epoch": 2.77, "learning_rate": 1.5980629539951576e-06, "loss": 0.1582, "step": 796 }, { "epoch": 2.78, "learning_rate": 1.5738498789346248e-06, "loss": 0.1714, "step": 797 }, { "epoch": 2.78, "learning_rate": 1.5496368038740922e-06, "loss": 0.177, "step": 798 }, { "epoch": 2.78, "learning_rate": 1.5254237288135596e-06, "loss": 0.1763, "step": 799 }, { "epoch": 2.79, "learning_rate": 1.5012106537530268e-06, "loss": 0.1807, "step": 800 }, { "epoch": 2.79, "learning_rate": 1.476997578692494e-06, "loss": 0.1719, "step": 801 }, { "epoch": 2.79, "learning_rate": 1.4527845036319612e-06, "loss": 0.1707, "step": 802 }, { "epoch": 2.8, "learning_rate": 1.4285714285714286e-06, "loss": 0.1621, "step": 803 }, { "epoch": 2.8, "learning_rate": 1.404358353510896e-06, "loss": 0.1653, "step": 804 }, { "epoch": 2.8, "learning_rate": 1.3801452784503632e-06, "loss": 0.1653, "step": 805 }, { "epoch": 2.81, "learning_rate": 1.3559322033898307e-06, "loss": 0.1692, "step": 806 }, { "epoch": 2.81, "learning_rate": 1.3317191283292979e-06, "loss": 0.1707, "step": 807 }, { "epoch": 2.82, "learning_rate": 1.3075060532687653e-06, "loss": 0.1621, "step": 808 }, { "epoch": 2.82, "learning_rate": 1.2832929782082327e-06, "loss": 0.177, "step": 809 }, { "epoch": 2.82, "learning_rate": 1.2590799031476999e-06, "loss": 0.178, "step": 810 }, { "epoch": 2.83, "learning_rate": 1.234866828087167e-06, "loss": 0.1724, "step": 811 }, { "epoch": 2.83, "learning_rate": 1.2106537530266345e-06, "loss": 0.1655, "step": 812 }, { "epoch": 2.83, "learning_rate": 1.186440677966102e-06, "loss": 0.1765, "step": 813 }, { "epoch": 2.84, "learning_rate": 1.162227602905569e-06, "loss": 0.1646, "step": 814 }, { "epoch": 2.84, "learning_rate": 1.1380145278450363e-06, "loss": 0.1753, "step": 815 }, { "epoch": 2.84, "learning_rate": 1.1138014527845037e-06, "loss": 0.1799, "step": 816 }, { "epoch": 2.85, "learning_rate": 1.0895883777239711e-06, "loss": 0.1743, "step": 817 }, { "epoch": 2.85, "learning_rate": 1.0653753026634383e-06, "loss": 0.1768, "step": 818 }, { "epoch": 2.85, "learning_rate": 1.0411622276029057e-06, "loss": 0.1785, "step": 819 }, { "epoch": 2.86, "learning_rate": 1.016949152542373e-06, "loss": 0.1675, "step": 820 }, { "epoch": 2.86, "learning_rate": 9.927360774818401e-07, "loss": 0.1743, "step": 821 }, { "epoch": 2.86, "learning_rate": 9.685230024213075e-07, "loss": 0.1704, "step": 822 }, { "epoch": 2.87, "learning_rate": 9.443099273607749e-07, "loss": 0.1687, "step": 823 }, { "epoch": 2.87, "learning_rate": 9.200968523002423e-07, "loss": 0.1741, "step": 824 }, { "epoch": 2.87, "learning_rate": 8.958837772397096e-07, "loss": 0.1777, "step": 825 }, { "epoch": 2.88, "learning_rate": 8.716707021791768e-07, "loss": 0.1643, "step": 826 }, { "epoch": 2.88, "learning_rate": 8.474576271186441e-07, "loss": 0.1763, "step": 827 }, { "epoch": 2.89, "learning_rate": 8.232445520581114e-07, "loss": 0.1816, "step": 828 }, { "epoch": 2.89, "learning_rate": 7.990314769975788e-07, "loss": 0.1699, "step": 829 }, { "epoch": 2.89, "learning_rate": 7.748184019370461e-07, "loss": 0.1619, "step": 830 }, { "epoch": 2.9, "learning_rate": 7.506053268765134e-07, "loss": 0.1753, "step": 831 }, { "epoch": 2.9, "learning_rate": 7.263922518159806e-07, "loss": 0.1685, "step": 832 }, { "epoch": 2.9, "learning_rate": 7.02179176755448e-07, "loss": 0.1716, "step": 833 }, { "epoch": 2.91, "learning_rate": 6.779661016949153e-07, "loss": 0.168, "step": 834 }, { "epoch": 2.91, "learning_rate": 6.537530266343826e-07, "loss": 0.1729, "step": 835 }, { "epoch": 2.91, "learning_rate": 6.295399515738499e-07, "loss": 0.1743, "step": 836 }, { "epoch": 2.92, "learning_rate": 6.053268765133172e-07, "loss": 0.1646, "step": 837 }, { "epoch": 2.92, "learning_rate": 5.811138014527845e-07, "loss": 0.1628, "step": 838 }, { "epoch": 2.92, "learning_rate": 5.569007263922519e-07, "loss": 0.1658, "step": 839 }, { "epoch": 2.93, "learning_rate": 5.326876513317192e-07, "loss": 0.1746, "step": 840 } ], "max_steps": 861, "num_train_epochs": 3, "total_flos": 819001106104320.0, "trial_name": null, "trial_params": null }